Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models

被引:3
|
作者
Dombrowski, Mischa [1 ]
Reynaud, Hadrien [2 ]
Baugh, Matthew [2 ]
Kainz, Bernhard [1 ,2 ]
机构
[1] Friedrich Alexander Univ Erlangen Nurnberg, Nurnberg, Germany
[2] Imperial Coll London, London, England
来源
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV | 2023年
关键词
D O I
10.1109/ICCV51070.2023.00097
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has been given a significant boost in result quality and ease of use. In this paper, we present a novel method that enables the generation of general foreground-background segmentation models from simple textual descriptions, without requiring segmentation labels. We leverage and explore pre-trained latent diffusion models, to automatically generate weak segmentation masks for concepts and objects. The masks are then used to fine-tune the diffusion model on an inpainting task, which enables fine-grained removal of the object, while at the same time providing a synthetic foreground and background dataset. We demonstrate that using this method beats previous methods in both discriminative and generative performance and closes the gap with fully supervised training while requiring no pixel-wise object labels. We show results on the task of segmenting four different objects (humans, dogs, cars, birds) and a use case scenario in medical image analysis. The code is available at https://github.com/MischaD/fobadiffusion.
引用
收藏
页码:988 / 998
页数:11
相关论文
共 50 条
  • [21] Learning Foreground-Background Segmentation from Improved Layered GANs
    Yang, Yu
    Bilen, Hakan
    Zou, Qiran
    Cheung, Wing Yin
    Ji, Xiangyang
    2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 366 - 375
  • [22] Performance of Foreground-Background Separation Algorithms for the Detection of Microbubbles in Super -Resolution Imaging
    Piepenbrock, Marion
    Dencks, Stefanie
    Schmitz, Georg
    2018 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IUS), 2018,
  • [23] A foreground/background separation algorithm for image compression
    Simard, PY
    Malvar, HS
    Rinker, J
    Renshaw, E
    DCC 2004: DATA COMPRESSION CONFERENCE, PROCEEDINGS, 2004, : 498 - 507
  • [24] Improving building rooftop segmentation accuracy through the optimization of UNet basic elements and image foreground-background balance
    Yang, Jian
    Matsushita, Bunkei
    Zhang, Haoran
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2023, 201 : 123 - 137
  • [25] FOREGROUND OBJECT SEGMENTATION FOR MOVING CAMERA SEQUENCES BASED ON FOREGROUND-BACKGROUND PROBABILISTIC MODELS AND PRIOR PROBABILITY MAPS
    Gallego, Jaime
    Bertolino, Pascal
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 3312 - 3316
  • [26] Panoramic Robust PCA for Foreground-Background Separation on Noisy, Free-Motion Camera Video
    Moore, Brian E.
    Gao, Chen
    Nadakuditi, Raj Rao
    IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING, 2019, 5 (02) : 195 - 211
  • [27] A Tensor Foreground-Background Separation Algorithm Based on Dynamic Dictionary Update and Active Contour Detection
    Pei, Shenglei
    Li, Linhao
    Ye, Lijuan
    Dong, Yongfeng
    IEEE ACCESS, 2020, 8 (08): : 88259 - 88272
  • [28] A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation
    Huynh Van Luong
    Joukovsky, Boris
    Eldar, Yonina C.
    Deligiannis, Nikos
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 1432 - 1436
  • [29] R-SpaRCS : An Algorithm for Foreground-Background Separation of Compressively-Sensed Surveillance Videos
    Ramesh, Lekshmi
    Shah, Pratik
    2015 12TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), 2015,
  • [30] Foreground-Background Audio Separation using Spectral Peaks based Time-Frequency Masks
    Bhattacharjee, Mrinmoy
    Prasanna, S. R. Mahadeva
    Guha, Prithwijit
    2022 IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATIONS, SPCOM, 2022,